Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

phind.com

Post reply on HN
Print view View original

281–290 of 358 posts

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#281

Post by jiggawatts »

SirMaster wrote: post #271
jiggawatts wrote: post #235

Earlier quoted context omitted.

In a sense you’re asking it the wrong questions. It’s a bit like asking Google “my PC crashed, how do I fix!?” and then expecting something specific to a rare issue in the first hit. Assuming a C# library even exists for what you’re doing (maybe not!) then still the best use of AI is to troubleshoot specific issues given an almost working piece of code as input . Ask it to explain why something doesn’t work instead o…

Even all of that is on the wrong track. There is nothing that I can see anywhere about controlling an ATV with the homekit accessory protocol.

Then you asked the wrong question.

AFAIK Apple generally does not allow arbitrary remote control (headless mode) for security reasons — it could be used for spam automation!

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#283

Post by throwaway4good »

Playing on the other AI prompt thread (https://news.ycombinator.com/item?id=38089247) here on HN I tried:

"write me an angry birds clone using JavaScript and the matter physics library"

And I really enjoyed the answer; in particular that it would show the sources for it - making it obvious how close its answer is openly available tutorials.

This is much better than a black box pretending to do black magic.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#284

Post by smusamashah »

Phind can be very good for general tech searches too. I spent long time looking for a way to disable my Pixel 4a from auto updating to android 14 (which it has already downloaded). With Google I only found one solution which disables update on restart. I asked the same in Phind and in one query I have got around 4 solutions [1].

[1]: https://www.phind.com/search?cache=vtzigjx3rnruc9ltocv9gqi1

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#285

Post by emptysongglass »

riku_iki wrote: post #95
Wytwwww wrote: post #90

Earlier quoted context omitted.

There is a performance conclusion in the title though.

That conclusion is based on benchmark with many examples in different tasks.

That conclusion is based on their benchmarks. I'm not interested in those. I'm interested in community benchmarks, like those we're seeing in the comments. Lo and behold, GPT-4 is still king. The claims of any company should be taken with exactly a pinch of salt.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#286

Post by riku_iki »

emptysongglass wrote: post #285
riku_iki wrote: post #95

Earlier quoted context omitted.

That conclusion is based on benchmark with many examples in different tasks.

That conclusion is based on their benchmarks. I'm not interested in those. I'm interested in community benchmarks, like those we're seeing in the comments. Lo and behold, GPT-4 is still king. The claims of any company should be taken with exactly a pinch of salt.

that benchmark(HumanEval) is some public benchmark built by others.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#289

Post by alex-moon »

I tried my standard "trick" question I use for LLMs:

"Give me five papers with code demonstrating the state of the art of machine learning which uses geospatial data (e.g. GeoJSON) as both input and output."

There is no such state of the art. My hand-wavey understanding is that GIS data is non-continuous, which makes it useless for transformers, and also contextual, which makes it useless for anything else. Will defer to actual ML people for better explanations.

Point is, LLMs invariably give five papers with code that don't actually exist - it's a guaranteed hallucination.

Phind was able to give me five links that do in fact exist, as well as contextual information as to why these five links were not papers with code doing ML with GIS data. This is by far the best answer to this question from an LLM I've received yet.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#290

Post by webappguy »

lmeyerov wrote: post #203
interstice wrote: post #98

If it’s trained on data (particularly docs) after 2021 that’s an automatic win over Chat GPT in some situations!

Gpt is 2023 now

Not general, at least not for me I still get 2021 notice unless I use bing in drop down
Post reply on HN